GPT Researcher MCP server

GPT Researcher MCP Server is a specialized service that enhances LLM applications with deep research capabilities. Unlike standard web search tools that return raw results requiring manual filtering, GPT Researcher autonomously explores multiple sources to deliver relevant, trusted, and up-to-date information optimized for LLM context windows.

Installation

Prerequisites

Before installing the MCP server, ensure you have:

• Python 3.10 or higher
• API keys for:
  • OpenAI API key
  • Tavily API key

Setup Instructions

1. Clone the repository:

   git clone https://github.com/assafelovic/gpt-researcher.git
   cd gpt-researcher
   

2. Install dependencies:

   cd gptr-mcp
   pip install -r requirements.txt
   

3. Set up environment variables:

   cp .env.example .env
   

4. Edit the .env file with your API keys:

   OPENAI_API_KEY=your_openai_api_key
   TAVILY_API_KEY=your_tavily_api_key
   

Running the Server

You can start the MCP server using one of two methods:

Method 1: Using Python directly

python server.py

Method 2: Using the MCP CLI

mcp run server.py

Integration with Claude

Claude Desktop Integration

To integrate with Claude Desktop on Mac:

1. Ensure your MCP server is running
2. Configure Claude Desktop by editing or creating the configuration file:

   ~/Library/Application Support/Claude/claude_desktop_config.json
   

3. Add your local GPT Researcher MCP server to the configuration
4. Restart Claude to apply changes

For detailed instructions, visit the Claude Desktop Integration guide.

Using GPT Researcher MCP

The server provides several powerful research tools:

Primary Tools

• deep_research: Conducts comprehensive web research on a topic, finding reliable and relevant information
• quick_search: Performs fast web searches optimized for speed over quality
• write_report: Generates reports based on research results
• get_research_sources: Retrieves sources used in the research
• get_research_context: Gets the full context of the research

Example Usage with Claude

When using with Claude, you can request research like this:

User: "I'm considering investing in NVIDIA. Can you research the current state of the company, recent stock performance, latest product announcements, and analyst opinions?"

Claude will then use the appropriate research tools to gather information and present a comprehensive analysis. The process takes approximately 30-40 seconds but delivers higher quality information than standard search tools.

Troubleshooting

If you encounter issues:

• Verify your API keys are correctly set in the .env file
• Confirm you're using Python 3.10 or higher
• Check that all dependencies are properly installed
• Review server logs for specific error messages

Getting Support

For additional assistance:

• Join the Community Discord
• Email: [email protected]

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.